Wang, Yixuan, Huang, Chao 
ORCID: 0000-0002-9300-1787, Wang, Zhilu, Xu, Shichao, Wang, Zhaoran and Zhu, Qi
(2021)
Cocktail: Learn a Better Neural Network Controller from Multiple Experts via Adaptive Mixing and Robust Distillation.
In: 2021 58th ACM/IEEE Design Automation Conference (DAC), 2021-12-5 - 2021-12-9, San Francisco.
|
Text
DAC_2021_Camera_ready.pdf - Author Accepted Manuscript Download (587kB) | Preview |
Abstract
Neural networks are being increasingly applied to control and decision making for learning-enabled cyber-physical systems (LE-CPSs). They have shown promising performance without requiring the development of complex physical models; however, their adoption is significantly hindered by the concerns on their safety, robustness, and efficiency. In this work, we propose COCKTAIL, a novel design framework that automatically learns a neural network based controller from multiple existing control methods (experts) that could be either model-based or neural network based. In particular, COCKTAIL first performs reinforcement learning to learn an optimal system-level adaptive mixing strategy that incorporates the underlying experts with dynamically-assigned weights, and then conducts a teacher-student distillation with probabilistic adversarial training and regularization to synthesize a student neural network controller with improved control robustness (measured by a safe control rate metric with respect to adversarial attacks or measurement noises), control energy efficiency, and verifiability (measured by the computation time for verification). Experiments on three non-linear systems demonstrate significant advantages of our approach on these properties over various baseline methods.
| Item Type: | Conference or Workshop Item (Unspecified) |
|---|---|
| Uncontrolled Keywords: | Behavioral and Social Science, Basic Behavioral and Social Science, Neurosciences, 7 Affordable and Clean Energy |
| Divisions: | Faculty of Science and Engineering > School of Electrical Engineering, Electronics and Computer Science |
| Depositing User: | Symplectic Admin |
| Date Deposited: | 14 Sep 2021 13:28 |
| Last Modified: | 15 Mar 2024 17:58 |
| DOI: | 10.1109/dac18074.2021.9586148 |
| Related URLs: | |
| URI: | https://livrepository.liverpool.ac.uk/id/eprint/3137060 |
Dimensions
Dimensions
